* [Bug 1892081] Re: Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions
2020-08-18 18:36 [Bug 1892081] [NEW] Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions Ahmed Karaman
@ 2020-08-18 18:37 ` Ahmed Karaman
2020-08-18 18:37 ` Ahmed Karaman
` (4 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Ahmed Karaman @ 2020-08-18 18:37 UTC (permalink / raw)
To: qemu-devel
** Attachment added: "before.png"
https://bugs.launchpad.net/qemu/+bug/1892081/+attachment/5402578/+files/before.png
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1892081
Title:
Performance improvement when using "QEMU_FLATTEN" with softfloat type
conversions
Status in QEMU:
New
Bug description:
Attached below is a matrix multiplication program for double data
types. The program performs the casting operation "(double)rand()"
when generating random numbers.
This operation calls the integer to float softfloat conversion
function "int32_to_float_64".
Adding the "QEMU_FLATTEN" attribute to the function definition
decreases the instructions per call of the function by about 63%.
Attached are before and after performance screenshots from
KCachegrind.
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1892081/+subscriptions
^ permalink raw reply [flat|nested] 7+ messages in thread* [Bug 1892081] Re: Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions
2020-08-18 18:36 [Bug 1892081] [NEW] Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions Ahmed Karaman
2020-08-18 18:37 ` [Bug 1892081] " Ahmed Karaman
@ 2020-08-18 18:37 ` Ahmed Karaman
2020-10-18 20:26 ` Richard Henderson
` (3 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Ahmed Karaman @ 2020-08-18 18:37 UTC (permalink / raw)
To: qemu-devel
** Attachment added: "after.png"
https://bugs.launchpad.net/qemu/+bug/1892081/+attachment/5402579/+files/after.png
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1892081
Title:
Performance improvement when using "QEMU_FLATTEN" with softfloat type
conversions
Status in QEMU:
New
Bug description:
Attached below is a matrix multiplication program for double data
types. The program performs the casting operation "(double)rand()"
when generating random numbers.
This operation calls the integer to float softfloat conversion
function "int32_to_float_64".
Adding the "QEMU_FLATTEN" attribute to the function definition
decreases the instructions per call of the function by about 63%.
Attached are before and after performance screenshots from
KCachegrind.
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1892081/+subscriptions
^ permalink raw reply [flat|nested] 7+ messages in thread* [Bug 1892081] Re: Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions
2020-08-18 18:36 [Bug 1892081] [NEW] Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions Ahmed Karaman
2020-08-18 18:37 ` [Bug 1892081] " Ahmed Karaman
2020-08-18 18:37 ` Ahmed Karaman
@ 2020-10-18 20:26 ` Richard Henderson
2021-05-04 19:39 ` Thomas Huth
` (2 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Richard Henderson @ 2020-10-18 20:26 UTC (permalink / raw)
To: qemu-devel
Confirmed, although "65% decrease" is on 0.44% of the total
execution for this test case, so the decrease isn't actually
noticeable.
Nevertheless, it's a simple enough change.
** Changed in: qemu
Status: New => In Progress
** Changed in: qemu
Assignee: (unassigned) => Richard Henderson (rth)
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1892081
Title:
Performance improvement when using "QEMU_FLATTEN" with softfloat type
conversions
Status in QEMU:
In Progress
Bug description:
Attached below is a matrix multiplication program for double data
types. The program performs the casting operation "(double)rand()"
when generating random numbers.
This operation calls the integer to float softfloat conversion
function "int32_to_float_64".
Adding the "QEMU_FLATTEN" attribute to the function definition
decreases the instructions per call of the function by about 63%.
Attached are before and after performance screenshots from
KCachegrind.
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1892081/+subscriptions
^ permalink raw reply [flat|nested] 7+ messages in thread* [Bug 1892081] Re: Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions
2020-08-18 18:36 [Bug 1892081] [NEW] Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions Ahmed Karaman
` (2 preceding siblings ...)
2020-10-18 20:26 ` Richard Henderson
@ 2021-05-04 19:39 ` Thomas Huth
2021-06-23 17:32 ` Richard Henderson
2021-08-25 7:17 ` Thomas Huth
5 siblings, 0 replies; 7+ messages in thread
From: Thomas Huth @ 2021-05-04 19:39 UTC (permalink / raw)
To: qemu-devel
This is an automated cleanup. This bug report has been moved to QEMU's
new bug tracker on gitlab.com and thus gets marked as 'expired' now.
Please continue with the discussion here:
https://gitlab.com/qemu-project/qemu/-/issues/134
** Changed in: qemu
Status: In Progress => Expired
** Changed in: qemu
Assignee: Richard Henderson (rth) => (unassigned)
** Bug watch added: gitlab.com/qemu-project/qemu/-/issues #134
https://gitlab.com/qemu-project/qemu/-/issues/134
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1892081
Title:
Performance improvement when using "QEMU_FLATTEN" with softfloat type
conversions
Status in QEMU:
Expired
Bug description:
Attached below is a matrix multiplication program for double data
types. The program performs the casting operation "(double)rand()"
when generating random numbers.
This operation calls the integer to float softfloat conversion
function "int32_to_float_64".
Adding the "QEMU_FLATTEN" attribute to the function definition
decreases the instructions per call of the function by about 63%.
Attached are before and after performance screenshots from
KCachegrind.
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1892081/+subscriptions
^ permalink raw reply [flat|nested] 7+ messages in thread* [Bug 1892081] Re: Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions
2020-08-18 18:36 [Bug 1892081] [NEW] Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions Ahmed Karaman
` (3 preceding siblings ...)
2021-05-04 19:39 ` Thomas Huth
@ 2021-06-23 17:32 ` Richard Henderson
2021-08-25 7:17 ` Thomas Huth
5 siblings, 0 replies; 7+ messages in thread
From: Richard Henderson @ 2021-06-23 17:32 UTC (permalink / raw)
To: qemu-devel
** Changed in: qemu
Status: Expired => Fix Committed
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1892081
Title:
Performance improvement when using "QEMU_FLATTEN" with softfloat type
conversions
Status in QEMU:
Fix Committed
Bug description:
Attached below is a matrix multiplication program for double data
types. The program performs the casting operation "(double)rand()"
when generating random numbers.
This operation calls the integer to float softfloat conversion
function "int32_to_float_64".
Adding the "QEMU_FLATTEN" attribute to the function definition
decreases the instructions per call of the function by about 63%.
Attached are before and after performance screenshots from
KCachegrind.
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1892081/+subscriptions
^ permalink raw reply [flat|nested] 7+ messages in thread* [Bug 1892081] Re: Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions
2020-08-18 18:36 [Bug 1892081] [NEW] Performance improvement when using "QEMU_FLATTEN" with softfloat type conversions Ahmed Karaman
` (4 preceding siblings ...)
2021-06-23 17:32 ` Richard Henderson
@ 2021-08-25 7:17 ` Thomas Huth
5 siblings, 0 replies; 7+ messages in thread
From: Thomas Huth @ 2021-08-25 7:17 UTC (permalink / raw)
To: qemu-devel
** Changed in: qemu
Status: Fix Committed => Fix Released
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1892081
Title:
Performance improvement when using "QEMU_FLATTEN" with softfloat type
conversions
Status in QEMU:
Fix Released
Bug description:
Attached below is a matrix multiplication program for double data
types. The program performs the casting operation "(double)rand()"
when generating random numbers.
This operation calls the integer to float softfloat conversion
function "int32_to_float_64".
Adding the "QEMU_FLATTEN" attribute to the function definition
decreases the instructions per call of the function by about 63%.
Attached are before and after performance screenshots from
KCachegrind.
To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1892081/+subscriptions
^ permalink raw reply [flat|nested] 7+ messages in thread
